Abstract
Purpose: To evaluate diagnostic accuracy of conventional radiography (CXR) and machine learning enhanced CXR (mlCXR) for the detection and quantification of disease-extent in COVID-19 patients compared to chest-CT. Methods: Real-time polymerase chain reaction (rt-PCR)-confirmed COVID-19-patients undergoing CXR from March to April 2020 together with COVID-19 negative patients as control group were retrospectively included. Two independent readers assessed CXR and mlCXR images for presence, disease extent and type (consolidation vs. ground-glass opacities (GGOs) of COVID-19-pneumonia. Further, readers had to assign confidence levels to their diagnosis. CT obtained ≤ 36 h from acquisition of CXR served as standard of reference. Inter-reader agreement, sensitivity for detection and disease extent of COVID-19-pneumonia compared to CT was calculated. McNemar test was used to test for significant differences. Results: Sixty patients (21 females; median age 61 years, range 38–81 years) were included. Inter-reader agreement improved from good to excellent when mlCXR instead of CXR was used (k = 0.831 vs. k = 0.742). Sensitivity for pneumonia detection improved from 79.5% to 92.3%, however, on the cost of specificity 100% vs. 71.4% (p = 0.031). Overall, sensitivity for the detection of consolidation was higher than for GGO (37.5% vs. 70.4%; respectively). No differences could be found in disease extent estimation between mlCXR and CXR, even though the detection of GGO could be improved. Diagnostic confidence was better on mlCXR compared to CXR (p = 0.013). Conclusion: In line with the current literature, the sensitivity for detection and quantification of COVID-19-pneumonia was moderate with CXR and could be improved when mlCXR was used for image interpretation.
Highlights
As the COVID-19 pandemic caused by severe acute respiratory syndrome (SARS)-CoV-2 spreads in the world, there is growing interest in the role and appropriateness of conventional chest radiographs (CXR) and computed tomography (CT) for management of patients with suspected or known COVID-19 infection
Patients suffered from the following comorbidities: Cardiovascular disease (19.5%), arterial hypertension (31.7%), diabetes (26.8%), chronic renal dysfunction (22.0%), and chronic pulmonary disease (7.3%)
Using Machine learning enhanced CXR (mlCXR) for image interpretation improved the sensitivity to 92.3% with a decline in specificity to 71.4%
Summary
As the COVID-19 pandemic caused by SARS-CoV-2 spreads in the world, there is growing interest in the role and appropriateness of conventional chest radiographs (CXR) and computed tomography (CT) for management of patients with suspected or known COVID-19 infection. As the chest CT and CXR imaging pattern is non-specific and overlaps with other infections, the diagnostic value of imaging for COVID-19 is low and dependents upon radiographic interpretation. Other studies have identified chest CT abnormalities in patients prior to the detection of SARS-CoV-2 RNA. Given the variability in chest imaging findings, the American College of Radiology (ACR) does not recommend chest radiographs or CT alone for the diagnosis of or screening for COVID-19 [2]. The findings on chest imaging in COVID-19 are non- specific and overlap with other infections, including influenza, H1N1, severe acute respiratory syndrome (SARS) and Middle East respiratory syndrome (MERS) [3,4]. Detection of SARS-CoV-2 RNA is required, even if radiologic findings are suggestive of COVID-19 on CXR or CT [2]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
